One shot contact learning

Marek Kopicki; Jeremy L Wyatt

One shot contact learning

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present a general method for one-shot learning of dexterous grasps and object placement. We rely on a product of experts formulation. Experts in the product are of two types. The first is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second is the hand configuration model and is a density over the whole hand configuration. Grasp generation for a novel object optimises the product of these two model types. Selection between grasp types is also automatic. The success rate is 84.4% or 77.7% if seven views or a single view of the test object are taken. We also show initial results on object placement.

Original language	English
Title of host publication	RSS 2015 Workshop Bridging the Gap between Data-driven and Analytical Physics-based Grasping and Manipulation
Publication status	Published - 16 Jul 2015

Access to Document

http://www.csc.kth.se/rss2015workshop/MarekKopickiRSS2015ws.pdf

FP7_COLLAB_PACMAN
Wyatt, J. (Principal Investigator) & Leonardis, A. (Co-Investigator)
European Commission, European Commission - Management Costs
1/03/13 → 29/02/16
Project: Research

Cite this

@inproceedings{6526549813064e9e84efb13cc0714966,

title = "One shot contact learning",

abstract = "We present a general method for one-shot learning of dexterous grasps and object placement. We rely on a product of experts formulation. Experts in the product are of two types. The first is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second is the hand configuration model and is a density over the whole hand configuration. Grasp generation for a novel object optimises the product of these two model types. Selection between grasp types is also automatic. The success rate is 84.4% or 77.7% if seven views or a single view of the test object are taken. We also show initial results on object placement.",

author = "Marek Kopicki and Wyatt, {Jeremy L}",

year = "2015",

month = jul,

day = "16",

language = "English",

booktitle = "RSS 2015 Workshop Bridging the Gap between Data-driven and Analytical Physics-based Grasping and Manipulation",

}

TY - GEN

T1 - One shot contact learning

AU - Kopicki, Marek

AU - Wyatt, Jeremy L

PY - 2015/7/16

Y1 - 2015/7/16

N2 - We present a general method for one-shot learning of dexterous grasps and object placement. We rely on a product of experts formulation. Experts in the product are of two types. The first is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second is the hand configuration model and is a density over the whole hand configuration. Grasp generation for a novel object optimises the product of these two model types. Selection between grasp types is also automatic. The success rate is 84.4% or 77.7% if seven views or a single view of the test object are taken. We also show initial results on object placement.

AB - We present a general method for one-shot learning of dexterous grasps and object placement. We rely on a product of experts formulation. Experts in the product are of two types. The first is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second is the hand configuration model and is a density over the whole hand configuration. Grasp generation for a novel object optimises the product of these two model types. Selection between grasp types is also automatic. The success rate is 84.4% or 77.7% if seven views or a single view of the test object are taken. We also show initial results on object placement.

M3 - Conference contribution

BT - RSS 2015 Workshop Bridging the Gap between Data-driven and Analytical Physics-based Grasping and Manipulation

ER -

One shot contact learning

Abstract

Access to Document

Fingerprint

Projects

FP7_COLLAB_PACMAN

Cite this